This release significantly enhances agent security with stronger worktree isolation and improved permission checks, preventing unintended actions by subagents and ensuring safe inter-agent communication. Users will benefit from numerous reliability fixes, including stable connectivity behind proxies, accurate usage credit requests, corrected usage attribution, and reliable streaming. Additional improvements include more precise pull request linking, better diff viewing using raw Git content, and improved screen reader support, offering a more robust and dependable experience for all users.
Improved3
- Improved auto mode safety: messages sent to other agent sessions via `SendMessage` are now evaluated by the permission classifier before dispatch
- Improved the refusal when Claude tries to invoke a skill with `disable-model-invocation`: Claude is now told to ask you to run the skill instead of replicating its workflow
- Improved the `/diff` view, the Remote Control workspace diff, and file-edit diffs in Claude Code on the web sessions to use raw git blob content, ignoring workspace-configured diff drivers and textconv
Changed1
- Changed Remote Control auto-start so repo-local settings (`.claude/settings.json` or `.claude/settings.local.json`) can no longer turn it on (they can still turn it off); enable it at user scope via `/config`
Fixed16
- Fixed worktree-isolated sessions and their subagents being able to run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type
- Fixed PreToolUse auto-allow hooks bypassing tool restrictions in background agent tasks (summaries, compaction, renames)
- Fixed `/usage-credits` on Team and Enterprise showing "you've already sent a usage credit request" for members whose earlier request was dismissed, blocking them from sending a new one
- Fixed the startup connectivity check hanging and then failing behind an HTTPS proxy; it now uses the same proxy-aware transport as API requests and times out with a clear message
- Fixed "Connection closed mid-response" errors being reported on responses that had actually completed
- Fixed `/usage` overattributing usage to MCP servers: a server's share now reflects only the requests that actually consumed its tool results, instead of every turn after any call to it
- Fixed sessions not linking to pull requests created after the branch was pushed, including through the GitHub REST API
- Fixed org-restricted `model: opus`-style subagent and teammate family aliases dropping to the parent model instead of stepping down to the newest org-allowed model in the family
- Fixed stream idle timeout firing on custom `ANTHROPIC_BASE_URL` gateways despite server keep-alive pings arriving on the wire
- Fixed claude.ai connectors being falsely marked as needing authorization when the session token is invalid — they now show a `/login` hint instead
- Fixed tool errors not being displayed for tools no longer available locally, for example after an MCP server is removed
- Fixed `SendMessage` rejecting a long summary — it now truncates instead, so sends no longer fail on a character limit
- Fixed the spinner's effort label in a subagent's transcript view showing the session's effort level instead of the subagent's own `effort:` setting
- Fixed rare crashes when a file watcher hit a filesystem error or during file-watcher teardown
- Fixed screen readers re-reading the whole input line on every backspace in `--ax-screen-reader` mode — end-of-line deletions now echo just the deleted characters
- Fixed host model-selection keys not taking precedence over a stale on-disk `managed-settings.json` when `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` is set
Removed1
- Removed ultraplan feature
Earlier 2.1.222 release · August 4, 2026
Improved3
- Improved auto mode safety: messages sent to other agent sessions via `SendMessage` are now evaluated by the permission classifier before dispatch
- Improved the refusal when Claude tries to invoke a skill with `disable-model-invocation`: Claude is now told to ask you to run the skill instead of replicating its workflow
- Improved the `/diff` view, the Remote Control workspace diff, and file-edit diffs in Claude Code on the web sessions to use raw git blob content, ignoring workspace-configured diff drivers and textconv
Changed1
- Changed Remote Control auto-start so repo-local settings (`.claude/settings.json` or `.claude/settings.local.json`) can no longer turn it on (they can still turn it off); enable it at user scope via `/config`
Fixed16
- Fixed worktree-isolated sessions and their subagents being able to run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type
- Fixed PreToolUse auto-allow hooks bypassing tool restrictions in background agent tasks (summaries, compaction, renames)
- Fixed `/usage-credits` on Team and Enterprise showing "you've already sent a usage credit request" for members whose earlier request was dismissed, blocking them from sending a new one
- Fixed the startup connectivity check hanging and then failing behind an HTTPS proxy; it now uses the same proxy-aware transport as API requests and times out with a clear message
- Fixed "Connection closed mid-response" errors being reported on responses that had actually completed
- Fixed `/usage` overattributing usage to MCP servers: a server's share now reflects only the requests that actually consumed its tool results, instead of every turn after any call to it
- Fixed sessions not linking to pull requests created after the branch was pushed, including through the GitHub REST API
- Fixed org-restricted `model: opus`-style subagent and teammate family aliases dropping to the parent model instead of stepping down to the newest org-allowed model in the family
- Fixed stream idle timeout firing on custom `ANTHROPIC_BASE_URL` gateways despite server keep-alive pings arriving on the wire
- Fixed claude.ai connectors being falsely marked as needing authorization when the session token is invalid — they now show a `/login` hint instead
- Fixed tool errors not being displayed for tools no longer available locally, for example after an MCP server is removed
- Fixed `SendMessage` rejecting a long summary — it now truncates instead, so sends no longer fail on a character limit
- Fixed the spinner's effort label in a subagent's transcript view showing the session's effort level instead of the subagent's own `effort:` setting
- Fixed rare crashes when a file watcher hit a filesystem error or during file-watcher teardown
- Fixed screen readers re-reading the whole input line on every backspace in `--ax-screen-reader` mode — end-of-line deletions now echo just the deleted characters
- Fixed host model-selection keys not taking precedence over a stale on-disk `managed-settings.json` when `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` is set
Removed1
- Removed ultraplan feature
Never miss a Claude Code release.
Get a push notification the moment the next version ships.
Get Claude DropsNew to the changelog? Read our guide to reading the Claude Code changelog or browse all releases.